LOCAL AIregistry
‹ all GPUs

Radeon RX 6800 XT

AMD · 16 GB · 512 GB/s
The recipe
Recommended
Qwen3.5-9B
GGUF Q4_K_Mllama.cpp64K context

Best for Fast answers and light agent work on 8–12 GB cards.

67 tok/sdecode
–prefill
64Kcontext
ThinksToolsLong context
Earlier check · Sep 10, 2026